Computational models on quantitative prediction of bioactivity of HIV-1 integrase 3’ processing inhibitors
Kong, Y.; Xuan, S.; Yan A.*
SAR and QSAR in Environmental Research, 2014, 25(9), 729-746.
在本研究中， 我们建立了四个定量构效关系 (QSAR) 计算模型来预测HIV-1整合酶的链切割过程(3'p) 抑制剂的生物活性。 收集了453种经放射性标记法检测具有生物活性值的抑制剂化合物。分子结构用MOE描述符表示，共选择了21个描述符用于建模。 采用两种方法, 将所有抑制剂划分为训练集和测试集：(1)采用Kohonen自组织映射 (SOM) 方法; (2) 通过随机选择。对于每个训练集和测试集，分别采用多元线性回归 (MLR) 分析和支持向量机 (SVM) 建模。 对于SOM分割的训练/测试集，相关系数 (r) 均大于0.84; 对于随机分割的训练/测试集，相关系数 (r) 均大于0.86。 一些分子性质如氢键供体容量、原子部分电荷性质、分子折射率、芳香键数和分子比表面积、体积和形状性质等对HIV-1整合酶的3'p步骤起着重要的抑制作用。
In this study, four computational quantitative structure–activity relationship (QSAR) models were built to predict the bioactivity of 3’ processing (3’P) inhibitors of HIV-1 integrase. Some 453 inhibitors whose bioactivity values were detected by the radiolabelling method were collected. The molecular structures were represented with MOE descriptors. In total, 21 descriptors were selected for modelling. All inhibitors were divided into a training set and a test set with two methods: (1) by a Kohonen’s self-organizing map (SOM); (2) by a random selection. For every training set and test set, a multilinear regression (MLR) analysis and a support vector machine (SVM) were used to establish models, respectively. For the training/test set divided by SOM, the correlation coefficients (r) were over 0.84, and for the training/test set split randomly, the r values were over 0.86. Some molecular properties such as hydrogen bond donor capacity, atomic partial charge properties, molecular refractivity, the number of aromatic bonds and molecular surface area, volume and shape properties played important roles for inhibiting 3’ processing step of HIV-1 integrase.
QSAR Models performance: Dataset (453 3’P inhibitors of HIV-1 Integrase)
|Model Name||Algorithm||Descriptors||Spliting method||Training set numbers||Training set r||Training set RMSE||Training set MAE||Test set numbers||Test set r||Test set RMSE||Test set MAE|
|Model 1A||MLR||21 MOE descriptors||Kohonen’s self-organizing map (SOM)||292||0.88||0.23||0.20||161||0.84||0.18||0.23|
|Model 2A||MLR||21 MOE descriptors||Random||292||0.87||0.22||0.20||161||0.86||0.19||0.23|
|Model 1B||SVM||21 MOE descriptors||Kohonen’s self-organizing map (SOM)||292||0.94||0.16||0.14||161||0.86||0.17||0.21|
|Model 2B||SVM||21 MOE descriptors||Random||292||0.87||0.22||0.20||161||0.86||0.19||0.23|